RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기

    다시기 참조 기반 과거 흑백 항공사진의 컬러화 및 초해상도 복원 = Multi-Temporal Reference-Guided Colorization and Super-Resolution of Historical Panchromatic Aerial Photographs

    한글로보기

    https://www.riss.kr/link?id=T17557286

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
      • URL 복사
    • 오류접수
    인용문이 복사되었습니다.

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    This dissertation proposes a multi-temporal reference-guided framework that integrates colorization and super-resolution for restoring historical panchromatic aerial photographs under ground-truth-absent conditions. Unlike conventional image enhancement, it treats aerial photographs as geospatial data and therefore preserves their coordinate reference system, ground sampling distance, and GeoTIFF metadata throughout restoration. The main contribution is a geospatially consistent restoration pipeline that couples multi-temporal color references, change-aware color transfer, comparative super-resolution, metadata-preserving GeoTIFF/BigTIFF output, and a multi-layer evaluation strategy that addresses the absence of contemporaneous color ground truth.
    The study targets Yeonje-gu, Busan, using three panchromatic epochs(1995, 1999, 2002) as restoration targets and three color epochs(2004, 2008, 2010) as references aligned to a common 2004 grid. Change detection separates stable and changed areas. In stable areas, chromatic information from the multi-temporal references is transferred with relatively higher confidence, whereas changed areas are estimated more cautiously using a K-means-based multi-temporal color palette; in both cases the original luminance is preserved and only the chromatic components are estimated, confining the risk of plausible but misleading hallucination to the chromatic dimension. On the colorized outputs, three ×2 models—SwinIR, BSRGAN, and RealESRGAN—are compared under identical conditions, and all products are stored as BigTIFF with updated affine transforms for direct use in GIS.
    Because no contemporaneous ground truth exists for the target epochs, results are interpreted through an uncertainty-aware, multi-layer evaluation—synthetic-pair and leave-one-out cross-validation, self-consistency, no-reference metrics, and change-based inspection-priority maps—rather than as claims of absolute color accuracy. Detected change ratios decrease monotonically with temporal distance (17.41%→15.10%→13.95%), the changed-area HSV KL divergence likewise decreases (1.751→1.331→1.067), and luminance consistency remains near 0.998. Cross-validation shows that the change-detection-and-palette mechanism yields a consistent gain (+0.594dB PSNR across all epochs), whereas the multi-temporal ensemble provides a larger but conditional benefit (+0.822dB on average, with an exception at the 2004 target); the super-resolution models exhibit clear trade-offs, implying use-dependent selection. The restored images are therefore algorithmic estimates that support archives and historical GIS as auxiliary geospatial layers, not substitutes for contemporaneous color photographs or legal survey records.
    번역하기

    This dissertation proposes a multi-temporal reference-guided framework that integrates colorization and super-resolution for restoring historical panchromatic aerial photographs under ground-truth-absent conditions. Unlike conventional image enhanceme...

    This dissertation proposes a multi-temporal reference-guided framework that integrates colorization and super-resolution for restoring historical panchromatic aerial photographs under ground-truth-absent conditions. Unlike conventional image enhancement, it treats aerial photographs as geospatial data and therefore preserves their coordinate reference system, ground sampling distance, and GeoTIFF metadata throughout restoration. The main contribution is a geospatially consistent restoration pipeline that couples multi-temporal color references, change-aware color transfer, comparative super-resolution, metadata-preserving GeoTIFF/BigTIFF output, and a multi-layer evaluation strategy that addresses the absence of contemporaneous color ground truth.
    The study targets Yeonje-gu, Busan, using three panchromatic epochs(1995, 1999, 2002) as restoration targets and three color epochs(2004, 2008, 2010) as references aligned to a common 2004 grid. Change detection separates stable and changed areas. In stable areas, chromatic information from the multi-temporal references is transferred with relatively higher confidence, whereas changed areas are estimated more cautiously using a K-means-based multi-temporal color palette; in both cases the original luminance is preserved and only the chromatic components are estimated, confining the risk of plausible but misleading hallucination to the chromatic dimension. On the colorized outputs, three ×2 models—SwinIR, BSRGAN, and RealESRGAN—are compared under identical conditions, and all products are stored as BigTIFF with updated affine transforms for direct use in GIS.
    Because no contemporaneous ground truth exists for the target epochs, results are interpreted through an uncertainty-aware, multi-layer evaluation—synthetic-pair and leave-one-out cross-validation, self-consistency, no-reference metrics, and change-based inspection-priority maps—rather than as claims of absolute color accuracy. Detected change ratios decrease monotonically with temporal distance (17.41%→15.10%→13.95%), the changed-area HSV KL divergence likewise decreases (1.751→1.331→1.067), and luminance consistency remains near 0.998. Cross-validation shows that the change-detection-and-palette mechanism yields a consistent gain (+0.594dB PSNR across all epochs), whereas the multi-temporal ensemble provides a larger but conditional benefit (+0.822dB on average, with an exception at the 2004 target); the super-resolution models exhibit clear trade-offs, implying use-dependent selection. The restored images are therefore algorithmic estimates that support archives and historical GIS as auxiliary geospatial layers, not substitutes for contemporaneous color photographs or legal survey records.

    더보기

    목차 (Table of Contents)

    • ABSTRACT v
    • 제1장 서론 1
    • 1.1 연구 배경 1
    • 1.2 연구 목적 및 목표 3
    • 1.3 연구 범위와 방법 5
    • ABSTRACT v
    • 제1장 서론 1
    • 1.1 연구 배경 1
    • 1.2 연구 목적 및 목표 3
    • 1.3 연구 범위와 방법 5
    • 1.4 논문 구성 9
    • 제2장 이론적 배경 및 선행연구 검토 10
    • 2.1 역사 항공사진 복원의 문제 성격 10
    • 2.2 컬러화 연구의 발전과 항공사진 적용 한계 12
    • 2.3 초해상도 연구의 발전과 항공사진 적용 한계 14
    • 2.4 컬러화·초해상도 결합 방식 선행연구 17
    • 2.5 다시기 참조와 변화인지 색상 추정 19
    • 2.6 정합·메타데이터 보존과 기준 부재 평가 21
    • 2.7 선행연구 종합과 연구 공백 24
    • 제3장 연구 자료 및 방법 26
    • 3.1 연구 자료와 기준 격자 26
    • 3.2 기준 부재 문제 정의 34
    • 3.3 파이프라인 개요 40
    • 3.4 정합과 메타데이터 보존 45
    • 3.5 변화인지 다시기 컬러화 47
    • 3.5.1 변화탐지와 마스크 산정 47
    • 3.5.2 RGB-HSV-Lab 특징 추출 51
    • 3.5.3 영역별 색차 이전과 블렌딩 56
    • 3.6 초해상도와 일관성 제어 60
    • 3.6.1 초해상도 모델 선정과 타일 추론 61
    • 3.6.2 순차 전이와 색 참조 기반 제어 65
    • 제4장 실험 결과 및 분석 68
    • 4.1 실험 환경 68
    • 4.2 평가지표와 의사결정 체계 71
    • 4.3 정합·변화탐지 결과 80
    • 4.4 컬러화 결과와 평가 90
    • 4.4.1 시기별 컬러화 결과 90
    • 4.4.2 LOO 합성 페어 검증 96
    • 4.5 초해상도 모델 비교와 권장 105
    • 4.6 통합 검증과 고찰 110
    • 제5장 결론 114
    • 5.1 연구 요약 114
    • 5.2 주요 연구 결과 115
    • 5.3 연구의 의의 및 활용 가능성 116
    • 5.4 연구의 한계 및 향후 연구 117
    • 5.5 종합 결론 119
    • 참 고 문 헌 121
    • 용 어 정 리 129
    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼